mlsanityData to 7 Oct 2026

Open challenges for Machine Learning based Early Decision-Making research

arXiv 2204.13111 ↗First posted 27 Apr 2022cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

More and more applications require early decisions, i.e. taken as soon as possible from partially observed data. However, the later a decision is made, the more its accuracy tends to improve, since the description of the problem to hand is enriched over time. Such a compromise between the earliness and the accuracy of decisions has been particularly studied in the field of Early Time Series Classification. This paper introduces a more general problem, called Machine Learning based Early Decision Making (ML-EDM), which consists in optimizing the decision times of models in a wide range of settings where data is collected over time. After defining the ML-EDM problem, ten challenges are identified and proposed to the scientific community to further research in this area. These challenges open important application perspectives, discussed in this paper.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 24 of its 109 references that are in the map. First posted on arXiv 27 Apr 2022.

Builds on

24 of 109 references.

References · 24

  1. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  2. 2016End to End Learning for Self-Driving Carscited by 1,000
  3. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  4. 2018Learning from positive and unlabeled data: a surveycited by 218
  5. 2016Multiple Instance Learning: A Survey of Problem Characteristics and Applicationscited by 163
  6. 2018Precision and Recall for Time Seriescited by 67
  7. 2017Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Carcited by 65
  8. 2020Approaches and Applications of Early Classification of Time Series: A Reviewcited by 39
  9. 2019Fake News Early Detection: An Interdisciplinary Studycited by 29
  10. 2020Friend or Faux: Graph-Based Early Detection of Fake Accounts on Social Networkscited by 19
  11. 2019Fire Now, Fire Later: Alarm-Based Systems for Prescriptive Process Monitoringcited by 18
  12. 2018Alarm-Based Prescriptive Process Monitoringcited by 16
12 more
  1. 2020From Weakly Supervised Learning to Biquality Learning: an Introductioncited by 10
  2. 2013Classifiers With a Reject Option for Early Time-Series Classificationcited by 9
  3. 2021Computer vision in automated parking systems: Design, implementation and challengescited by 9
  4. 2019Early Classification for Agricultural Monitoring from Satellite Time Seriescited by 7
  5. 2020Unsupervised Anomaly Detectors to Detect Intrusions in the Current Threat Landscapecited by 7
  6. 2021Unsupervised anomaly detection for a Smart Autonomous Robotic Assistant Surgeon (SARAS)using a deep residual autoencodercited by 6
  7. 2015Graphs in machine learning: an introductioncited by 4
  8. 2020Early Classification of Time Series. Cost-based Optimization Criterion and Algorithmscited by 4
  9. 2020Importance Reweighting for Biquality Learningcited by 4
  10. 2013Friend or Foe? Fake Profile Identification in Online Social Networkscited by 3
  11. 2021Early and Revocable Time Series Classificationcited by 3
  12. 2021Early Classification of Time Series is Meaningfulcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 3; 2026: 1.

6 papers.

  1. 2023Automatically Reconciling the Trade-off between Prediction Accuracy and Earliness in Prescriptive Business Process Monitoringcited by 4
  2. 2024Early Classification of Time Series: A Survey and Benchmarkcited by 3
  3. 2025Unsupervised Feature Construction for Anomaly Detection in Time Series -- An Evaluationcited by 1
  4. 2025Alert: Learning Trigger Functions for Early Classification of Time Series using Deep-RLcited by 1
  5. 2025TURBOTEST: Learning When Less is Enough through Early Termination of Internet Speed Testscited by 0
  6. 2026Early Classification of Time Series in Non-Stationary Cost Regimescited by 0